Procedural Generation and Modern ML Share the Same Ethos: Sampling Conditioned Distributions

keenanisalive · x · 2026-09-05

The author argues the spirit of classical procedural generators is not so different from contemporary ML: both draw samples from a distribution conditioned on user-defined parameters. Classical distributions can even be autoregressive, depending on earlier generation steps.

He adds that procedural generation of cities, plants, and other phenomena has existed for decades—a useful historical lens for modern generative models.

Related event: Classic procedural generation shares its core with modern ML, dev argues(2 posts)→

Original post →

More from Research

Research channel →